Search

Abstract This study presents an application of the self-organizing migrating algorithm (SOMA) to train artificial neural networks for skin segmentation tasks. We compare the performance of SOMA with popular gradient-based optimization methods such as ADAM and SGDM, as well as with another evolutionary algorithm, differential evolution (DE). Experiments are conducted on the skin dataset, which consists of 245,057 samples with skin and non-skin labels. The results show that the neural network trained by SOMA achieves the highest accuracy (93.18%), outperforming ADAM (84.87%), SGDM (84.79%), and DE (91.32%). The visual evaluation also reveals the SOMA-trained neural network’s accurate and reliable segmentation capabilities in most cases. These findings highlight the potential of incorporating evolutionary optimization algorithms like SOMA into the training process of artificial neural networks, significantly improving performance in image segmentation tasks.

This paper explores using and hybridizing simple prediction models to maximize the accuracy of local weather prediction while maintaining low computational effort and the need to process and acquire large volumes of data. A hybrid RF-LSTM model is proposed and evaluated in this research paper for the task of short-term local weather forecasting. The local weather stations are built within an acceptable radius of the measured area and are designed to provide a short period of forecasting - usually within one hour. The lack of local weather data might be problematic for an accurate short-term valuable prediction in sustainable applications like agriculture, transportation, energy management, and daily life. Weather forecasting is not trivial because of the non-linear nature of time series. Thus, traditional forecasting methods cannot predict the weather accurately. The advantage of the ARIMA model lies in forecasting the linear part, while the SVR model indicates the non-linear characteristic of the weather data. Both non-linear and linear approaches can represent the combined model. The hybrid ARIMA-SVR model strengthens the matched points of the ARIMA model and the SVR model in weather forecasting. The LSTM and random forest are both popular algorithms used for regression problems. LSTM is more suitable for tasks involving sequential data with long-term dependencies. Random Forest leverages the wisdom of crowds by combining multiple decision trees, providing robust predictions, and reducing overfitting. Hybrid Random forest-LSTM potentially leverages the robustness and feature importance of Random Forest along with the ability of LSTM to capture sequential dependencies. The comparison results show that the hybrid RF-LSTM model reduces the forecasting errors in metrics of MAE, R-squared, and RMSE. The proposed hybrid model can also capture the actual temperature trend in its prediction performance, which makes it even more relevant for many other possible decision-making steps in sustainable applications. Furthermore, this paper also proposes the design of a weather station based on a real-time edge IoT system. The RF-LSTM leverages the parallelized characteristics of each decision tree in the forest to accelerate the training process and faster inferences. Thus, the hybrid RF-LSTM model offers advantages in terms of faster execution speed and computational efficiency in both PC and Raspberry Pi boards. However, the RF-LSTM consumes the highest peak memory usage due to being a combination of two different models.

Can machine learning take a prediction to win an investment in ICO (Initial Coin Offering)? In this research work, our objective is to answer this question. Four popular and lower computational demanding approaches including Ridge regression (RR), Artificial neural network (ANN), Random forest regression (RFR), and a hybrid ANN-Ridge regression are compared in terms of accuracy metrics to predict ICO value after six months. We use a dataset collected from 109 ICOs that were obtained from the cryptocurrency websites after data preprocessing. The dataset consists of 12 fields covering the main factors that affect the value of an ICO. One-hot encoding technique is applied to convert the alphanumeric form into a binary format to perform better predictions; thus, the dataset has been expanded to 128 columns and 109 rows. Input data (variables) and ICO value are non-linear dependent. The Artificial neural network algorithm offers a bio-inspired mathematical model to solve the complex non-linear relationship between input variables and ICO value. The linear regression model has problems with overfitting and multicollinearity that make the ICO prediction inaccurate. On the contrary, the Ridge regression algorithm overcomes the correlation problem that independent variables are highly correlated to the output value when dealing with ICO data. Random forest regression does avoid overfitting by growing a large decision tree to minimize the prediction error. Hybrid ANN-Ridge regression leverages the strengths of both algorithms to improve prediction accuracy. By combining ANN’s ability to capture complex non-linear relationships with the regularization capabilities of Ridge regression, the hybrid can potentially provide better predictive performance compared to using either algorithm individually. After the training process with the cross-validation technique and the parameter fitting process, we obtained several models but selected three of the best in each algorithm based on metrics of RMSE (Root Mean Square Error), R2 (R-squared), and MAE (Mean Absolute Error). The validation results show that the presented Ridge regression approach has an accuracy of at most 99% of the actual value. The Artificial neural network predicts the ICO value with an accuracy of up to 98% of the actual value after six months. Additionally, the Random forest regression and the hybrid ANN-Ridge regression improve the predictive accuracy to 98% actual value.

In submitting conference proceedings to Engineering Proceedings, the volume editors of the proceedings certify to the publisher that all papers published in this volume have been subjected to peer review that was administered by the volume editors [...]

Mining frequent subgraphs is an interesting and important problem in the graph mining field, in that mining frequent subgraphs from a single large graph has been strongly developed, and has recently attracted many researchers. Among them, MNI-based approaches are considered as state-of-the-art, such as the GraMi algorithm. Besides frequent subgraph mining (FSM), frequent closed frequent subgraph mining was also developed. This has many practical applications and is a fundamental premise for many studies. This paper proposes the CloGraMi (Closed Frequent Subgraph Mining) algorithm based on GraMi to find all closed frequent subgraphs in a single large graph. Two effective strategies are also developed, the first one is a new level order traversal strategy to quickly determine closed subgraphs in the searching process, and the second is setting a condition for early pruning a large portion of non-closed candidates, both of them aim to reduce the running time as well as the memory requirements, improve the performance of the proposed algorithm. Our experiments are performed on five real datasets (both directed and undirected graphs) and the results show that the running time as well as the memory requirements of our algorithm are significantly better than those of the GraMi-based algorithm.

A social network is one of the efficient tools for information propagation. The content is the bridge between the product and its customers. Evaluating the user’s content creation is a valuable feature to improve information spreading on the social network. This paper proposes a method for extracting brand value with influencers by combining the user’s amplification and content creation in influencer marketing. The amplification factors are studied based on the propagation of the posts on the social network in a duration time. Those factors are more valuable than before when using influencer marketing at a determined time. Moreover, the content creation score is also studied to measure content creation based on the passion point with a brand and its quality. The amplification factors and content creation score are combined to analyze posts’ interest in detecting the emerging influent users for a product in the influencer marketing campaign. Using the amplification factors, the passion points, and the content creation score, a system to manage the influencer marketing on Facebook has been constructed and tested in the real-world campaign. The experimental results show that the proposed method’s influencers bring the conversion rate’s efficiency and revenue in the influencer marketing campaign.

In modern applications, large graphs are usually applied in the simulation and analysis of large complex systems such as social networks, computer networks, maps, traffic networks. Therefore, graph mining is also an interesting subject attracting many researchers. Among them, frequent subgraph mining in a single large graph is one of the most important branches of graph mining, it is defined as finding all subgraphs whose occurrences in a dataset are greater than or equal to a given frequency threshold. In which, the GraMi algorithm is considered the state of the art approach and many algorithms have been proposed to improve this algorithm. In 2020, the SoGraMi algorithm was proposed to optimize the GraMi algorithm and presented an outstanding performance in terms of runtime and storage space. In this paper, we propose a new algorithm to improve SoGraMi based on connected components, called CCGraMi (Connected Components GraMi). Our experiments on four real datasets (both directed and undirected) show that the proposed algorithm outperforms SoGraMi in terms of running time as well as memory requirements.

In recent months and years, with more and more computers and computer systems becoming the target of cyberattacks. These attacks are gaining strength and the sophistication of the approach in terms of how to attack. Attackers and Defenders are increasingly using artificial intelligence methods to maximize the success of their actions. For a successful defence, we must be able to anticipate future threats that may come. For these reasons, our research group is engaged in creating experimental software with artificial intelligence to test the possibilities and capabilities of such malware in the event of its deployment. This software has not only malware capabilities but also antimalware and can be used on both sides. This article introduces the reader to the main principles of our design, which can serve as a future platform for cyber defence systems.

To simulate some behavior of swarms, the malware was selected as a carrier of intelligence. This article describes the current solution which is fully virtual. This gives us a possibility to interfere environment and see how the improved malware will react. This common intention provides improvements related to docker images and also architectural that is related to code changes. Communication over network together with cooperation on particle level is a key part of this solution. Malware movements are the same as movements of swarm particles, which fully fit this requirement. Significance is also put on the swarming part, where the decision which swarms algorithm to utilize is crucial. The outcome from this work should be partly practical and theoretical related to environment setup, particles communication, movements and coordination which finally finishes in distributed denial of service (DDoS) coordinated attack via hypertext transfer protocol (HTTP) to some server. After this theoretical work, the practical simulation will be done to see if the swarm attack brings expected results.

This paper is discussing our new research direction in the Voynich manuscript research. While our previous papers have been dealing with the research that has been based on fractal property analyses or graph properties analyses, where the graph has been constructed from the Voynich manuscript word sequences (Fig. 1), this paper discusses another kind of research on Voynich manuscript. This research is focused on the compassion of the letters or alphabets from Voynich manuscript with another selected alphabets from a different dialect, in that case, dialect from the Indian language. The reason is to point out the possibility that we can identify the origin of the Voynich manuscript alphabets based on the graphical conversion between letters from different dialects. Because this research is a very wide and deep topic, we publish in this paper only basic ideas, simulations and discuss all problems which have been found during those experimentation as well as outlining of the future directions of the research in an outlined way.

With the rapid growth of technology in the digital landscape, cybercriminals attempt to utilize new and sophisticated techniques to autonomous and increase the speed and scale of their attacks. Meanwhile, the Dark Web infrastructures such as Tor, plays a crucial role in the criminal underground, especially for malware developers' communities. It is logical to expect that the malicious actors would utilize the combination of these techniques in shortcoming time. To better understand the upcoming threat, in this manuscript, we investigate the design and mitigation of such malware. Accordingly, we introduce X-sWarm, which will be the next generation of resilient, stealthy malware that leverages the intelligent technique and the darknet infrastructures. Furthermore, we show that with the self-healing network mechanism, X-sWarm can achieve a low diameter and a low degree and be robust to partitioning under node removal. More importantly, we suggest the mitigation technique that neutralizes the nodes of the proposed worm.

Recent developments in Artificial intelligence (AI) have a vast transformative potential for both cybersecurity defenders and cybercriminals. Anti-malware solutions adopt intelligent techniques to detect and prevent threats to the digital space. In contrast, cybercriminals are aware of the new prospects too and will probably try to use it in their activities. This survey aims at providing an overview on the way artificial intelligence can be used to power a malicious program that is: intelligent evasion techniques, autonomous malware, AI against itself, and applying bio-inspired computation and swarm intelligence.

Current commercial antivirus detection engines still rely on signature-based methods. However, with the huge increase in the number of new malware, current detection methods become not suitable. In this paper, we introduce a malware detection model based on ensemble learning. The model is trained using the minimum number of signification features that are extracted from the file header. Evaluations show that the ensemble models slightly outperform individual classification models. Experimental evaluations show that our model can predict unseen malware with an accuracy rate of 0.998 and with a false positive rate of 0.002. The paper also includes a comparison between the performance of the proposed model and with different machine learning techniques. We are emphasizing the use of machine learning based approaches to replace conventional signature-based methods.

In the fourth technology revolution, influencer marketing is an essential kind of digital marketing. This marketing uses identified influencers to viral the information of products to target customers. It is useful to support brands exposed to more valuable online consumers. The influencer marketing campaign needs a management system to manage on a social network. This system helps to increase the efficiency of a campaign. This paper proposes a management system for the influencer marketing campaign, called the ADVO system. This system provides a tool for collecting data on a social network and detecting potential brand influencers for the marketing campaign. The meaningful measures for users include amplification factors for evaluating the information propagation, the passion point to measure a user’s favorite when it comes to a brand, and the content creation score for determining the ability of post-content creating. The ADVO system helps the brand to make the decision through real-time visual reports of the campaign. It is a foundation to create commercial activities and construct an advocate community of the related brand.

This paper discusses the utilization of the complex chaotic dynamics given by the selected time-continuous chaotic systems as well as by the discrete chaotic maps, as the chaotic pseudo-random number generators and driving maps for the chaos based optimization. Such an optimization concept is utilizing direct output iterations of chaotic system transferred into the required numerical range as the replacement of traditional and default pseudo-random number generators, or this concept uses the chaotic dynamics for mapping the search space mostly within the smart hybrid local search techniques. This paper shows totally three groups of complex chaotic dynamics given by chaotic flows, oscillators and discrete maps. Simulations of examples of chaotic dynamics as unconventional generators or mapped to the search space were performed, and related issues like parametric plots, distributions of such a systems, periodicity, and dependency on internally available parameters are brie y discussed in this paper. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

In this paper, the dynamics of the selected variants of the differential evolution is modelled by aggregated network capturing the relationships between individuals established during the population evolution. The motivation of this research is to better understand the relationships between individuals of the selected variants of the differential evolution. Thanks to the analysis of the aggregated networks, the advantages as well as bottlenecks of the selected algorithms can be specified more precisely and the results of the analysis can be used to develop novel algorithms. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

In this article, a novel leader selection strategy for the self-organizing migrating algorithm is introduced. This strategy replaces original AllToOne and AllToRand strategies. It is shown and statistically tested, that the new strategy outperforms the original ones. All the experiments were conducted on well known CEC 2014 benchmark functions according to the CEC competition rules and reported here.

In this paper, we propose a new method named Pareto-based self-organizing migrating algorithm (SOMA Pareto), in which the algorithm is divided into the Organization, Migration, and Update processes. The important key in the Organization process is the application of the Pareto Principle to select the Migrant and the Leader, increasing the performance of the algorithm. The adaptive PRT, Step, and PRTVector parameters are applied to enhance the ability to search for promising subspaces and then to focus on exploiting that subspaces. Based on the testing results on the well-known benchmark suites such as CEC'13, CEC'15, and CEC'17, the superior performance of the proposed algorithm compared to the SOMA family and the state-of-the-art algorithms such as variant DE and PSO are confirmed. These results demonstrate that SOMA Pareto is an effective, promising algorithm.

This paper discusses the possible use of unconventional algorithms on analysis and categorization of the unknown text, including documents written in unknown languages. Scholars have identied about ten famous manuscripts, mostly encrypted or written in the unknown language. The most famous is the Voynich manuscript, an illustrated codex hand-written in an unknown language or writing system. Using carbon-dating methods, the researchers determined its age as the early 15th century (between 1404-1438). Many professional and amateur cryptographers have studied the Voynich manuscript, and none has deciphered its meaning as yet, including American and British code-breakers and cryptologists. While there exist many hypotheses about the meaning and structure of the document, they have yet to be conrmed empirically. In this paper, we discuss two dierent kinds of unconventional approaches for how to handle manuscripts with unidentied writing systems and determine whether its properties are characterized by a natural language, or is only historical fake text.

This research represents a detailed insight into the modern and popular hybridization of deterministic chaotic dynamics and evolutionary computation. It is aimed at the influence of chaotic sequences on the performance of four selected Differential Evolution (DE) variants. The variants of interest were: original DE/Rand/1/ and DE/Best/1/ mutation schemes, simple parameter adaptive jDE, and the recent state of the art version SHADE. Experiments are focused on the extensive investigation of the different randomization schemes for the selection of individuals in DE algorithm driven by the nine different two-dimensional discrete deterministic chaotic systems, as the chaotic pseudorandom number generators. The performances of DE variants and their chaotic/non-chaotic versions are recorded in the one-dimensional settings of 10D and 15 test functions from the CEC 2015 benchmark, further statistically analyzed.

In this study, we propose a repulsive mechanism for the Particle Swarm Optimization algorithm that improves its performance on multi-modal problems. The repulsive mechanism is further extended with a distance-based modification. The results are presented and tested for statistical significance. We discuss the observations and propose further directions for the research.

Automated comparison of faces in the photographs is a well established discipline. The main aim of this paper is to describe an approach whereby face recognition can be used in suggestion of a new contacts. The new contact suggestion is a common technique used across all main social networks. Our approach uses a freely available face comparison called "Betaface" together with our automated processig of the user´s Facebook profile. The research´s main point of interest is the comparison of friend´s facial images in a social network itself, how to process such a great amount of photos and what additional sources of data should be used. In this approach we used our automated processing algorithm Betaface in the social network Facebook and for the additional data, the Flickr social network was used. The results and their quality are discussed at the end.

In this paper, evolutionary technique Differential Evolution (DE) is used for the evolutionary tuning of controller parameters for the stabilization of selected discrete chaotic system, which is the two-dimensional Lozi map. The novelty of the approach is that the selected controlled discrete dissipative chaotic system is used within Chaos enhanced heuristic concept as the chaotic pseudo-random number generator to drive the mutation and crossover process in the DE. The idea was to utilize the hidden chaotic dynamics in pseudo-random sequences given by chaotic map to help Differential evolution algorithm in searching for the best controller settings for the same chaotic system. The optimizations were performed for three different required final behavior of the chaotic system, and two types of developed cost function. To confirm the robustness of presented approach, comparisons with canonical DE strategy and PSO algorithm have been performed.

A numerical method based on the Pontryagin maximum principle for solving an optimal control problem with static and dynamic phase constraints for a group of objects is considered. Dynamic phase constraints are introduced to avoid collisions between objects. Phase constraints are included in the functional in the form of smooth penalty functions. Additional parameters for special control modes and the terminal time of the control process were introduced. The search for additional parameters and the initial conditions for the conjugate variables was performed by the modified self-organizing migrating algorithm. An example of using this approach to solve the optimal control problem for the oncoming movement of two mobile robots is given. Simulation and comparison with direct approach showed that the problem is multimodal, and it approves application of the evolutionary algorithm for its solution.

Artificial intelligence techniques have grown rapidly in recent years, and their applications in practice can be seen in many fields, ranging from facial recognition to image analysis. In the cybersecurity domain, AI-based techniques can provide better cyber defense tools and help adversaries improve methods of attack. However, malicious actors are aware of the new prospects too and will probably attempt to use them for nefarious purposes. This survey paper aims at providing an overview of how artificial intelligence can be used in the context of cybersecurity in both offense and defense.

This paper presents an application of Markov Decision Process method for modeling of selected marketing processes. Based on available realistic data, MDP model is constructed. Customer behavior is represented by a set of states of the model with assigned rewards corresponding to the expected return value. Outcoming arcs then represent actions available to the customer in current state. Favourable outcome rate of available actions is then analyzed, with emphasis on suitability of the model for future predictions of customer behavior.

In this study, we construct a complex network from the inner dynamic of Particle Swarm Optimization algorithm. The subsequent analysis of the network promises to provide useful information for better understanding the dynamic of the swarm that is not acquirable by other means. We present several network visualizations and numerical analysis. We discuss the observations and propose further directions for the research.

In this article, we want to propose a new model of the network for analyzing the evolution algorithms. We focus on the graph called native visibility graph. We show how we can get a time series from the run of the self-organizing migrating algorithm and how we can convert these series into a network. At the end of the article, we focus on some basic network properties and we propose how can we use these properties for later investigation. All experiments run on well-known CEC 2016 benchmarks.

Evolutionary technique differential evolution (DE) is used for the evolutionary tuning of controller parameters for the stabilization of set of different chaotic systems. The novelty of the approach is that the selected controlled discrete dissipative chaotic system is used also as the chaotic pseudorandom number generator to drive the mutation and crossover process in the DE. The idea was to utilize the hidden chaotic dynamics in pseudorandom sequences given by chaotic map to help differential evolution algorithm search for the best controller settings for the very same chaotic system. The optimizations were performed for three different chaotic systems, two types of case studies and developed cost functions.

This paper deals with usage of an alternative tool for symbolic regression—analytic programming which is able to solve various problems from the symbolic domain, as well as genetic programming and grammatical evolution. This paper describes a setting of an optimal trajectory for a robot (originally designed as an artificial ant on Santa Fe trail) solved by means of analytic programming. Firstly, main principles of analytic programming are described and explained. The second part shows how analytic programming was used for the application of finding a suitable trajectory step by step. Because analytic programming needs evolutionary algorithms for its run, three evolutionary algorithms were used—self-organizing migrating algorithm, differential evolution, and simulated annealing—to show that anyone can be used. The total number of simulations was 150 and results show that the first two used algorithms were more successful than not so robust simulated annealing.